Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6148 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.5176. Min Act: -0.1700
Data Index: 3844266 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.5176. Min Act: -0.1700
Data Index: 8762544 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.4706. Min Act: -0.1700
Data Index: 2649705 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.4392. Min Act: -0.1700
Data Index: 6895685 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.4392. Min Act: -0.1700
Data Index: 624997 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.4236. Min Act: -0.1700
Data Index: 3620934 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.4079. Min Act: -0.1700
Data Index: 2186762 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.4236. Min Act: -0.1700
Data Index: 3196568 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.3765. Min Act: -0.1700
Data Index: 3230591 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.3765. Min Act: -0.1700
Data Index: 513532 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.3765. Min Act: -0.1700
Data Index: 299996 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.3608. Min Act: -0.1700
Data Index: 680397 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.3452. Min Act: -0.1700
Data Index: 6742460 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.3295. Min Act: -0.1700
Data Index: 7872505 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.2981. Min Act: -0.1700
Data Index: 4751724 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.2981. Min Act: -0.1700
Data Index: 880690 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.2824. Min Act: -0.1700
Data Index: 2370032 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.2981. Min Act: -0.1700
Data Index: 7987900 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.2824. Min Act: -0.1700
Data Index: 8187896 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5176. Min Range: -3.5176
Max Act: 3.2824. Min Act: -0.1700
Data Index: 3649769 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19